© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7621
    Prev
    Next
    INDEX
    Explanations

    geographical and directional terms

    oai_token-act-pair · gpt-3.5-turbo

    elements related to geographical and astronomical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.87
    apons
    -0.86
    pkg
    -0.81
    ittle
    -0.79
    shop
    -0.78
    Berry
    -0.77
    amily
    -0.75
    gotten
    -0.75
    Priv
    -0.74
    iability
    -0.74
    POSITIVE LOGITS
     latitude
    1.07
     orbits
    1.06
     orbit
    1.06
     align
    1.05
     coordinates
    1.01
     opposite
    0.99
     tilt
    0.95
     aligned
    0.93
     axis
    0.93
     angles
    0.90
    Activations Density 0.292%

    No Known Activations